|
697510
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd3f5baf-aa1a-49ce-91d7-884679e12ce0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd3f5baf-aa1a-49ce-91d7-884679e12ce0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348755.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348755.0 (TID 348755) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f931256f-83b1-4e5c-a438-7fe584927caa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348755.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348755.0 (TID 348755) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f931256f-83b1-4e5c-a438-7fe584927caa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697511
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd3f5baf-aa1a-49ce-91d7-884679e12ce0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd3f5baf-aa1a-49ce-91d7-884679e12ce0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348755]
|
|
|
697512
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 02574d6d-238e-4c19-b6a6-f07f494fbef3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 02574d6d-238e-4c19-b6a6-f07f494fbef3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348756.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348756.0 (TID 348756) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2fe5ef0-4229-43c3-83e3-daf25567a197-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348756.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348756.0 (TID 348756) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2fe5ef0-4229-43c3-83e3-daf25567a197-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697513
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 02574d6d-238e-4c19-b6a6-f07f494fbef3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 02574d6d-238e-4c19-b6a6-f07f494fbef3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348756]
|
|
|
697514
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 19524cbe-cff5-4309-9f6e-458eeb69543b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 19524cbe-cff5-4309-9f6e-458eeb69543b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348757.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348757.0 (TID 348757) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac2e9e63-83c0-40e1-a7fe-4e4fa718a3c4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348757.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348757.0 (TID 348757) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac2e9e63-83c0-40e1-a7fe-4e4fa718a3c4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697515
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 19524cbe-cff5-4309-9f6e-458eeb69543b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 19524cbe-cff5-4309-9f6e-458eeb69543b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348757]
|
|
|
697516
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7be7d485-1587-4822-8796-6814a6eb0b7f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7be7d485-1587-4822-8796-6814a6eb0b7f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348758.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348758.0 (TID 348758) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6b12679b-f773-4e6a-9d93-d14c5da3045a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348758.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348758.0 (TID 348758) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6b12679b-f773-4e6a-9d93-d14c5da3045a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697517
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7be7d485-1587-4822-8796-6814a6eb0b7f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7be7d485-1587-4822-8796-6814a6eb0b7f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348758]
|
|
|
697518
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30d49f0-d5e7-4c62-962b-4393c1ff6bfe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30d49f0-d5e7-4c62-962b-4393c1ff6bfe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348759.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348759.0 (TID 348759) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9fea8e15-6f8b-4fb6-be76-d776e824d1b3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348759.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348759.0 (TID 348759) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9fea8e15-6f8b-4fb6-be76-d776e824d1b3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697519
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30d49f0-d5e7-4c62-962b-4393c1ff6bfe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30d49f0-d5e7-4c62-962b-4393c1ff6bfe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
19 ms
|
|
[348759]
|
|
|
697520
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a9edc828-d2d0-442e-a9c8-7a5a0fdf1e4a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a9edc828-d2d0-442e-a9c8-7a5a0fdf1e4a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348760.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348760.0 (TID 348760) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cae30eb9-ca59-43e8-89ec-7fc5c2d90226-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348760.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348760.0 (TID 348760) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cae30eb9-ca59-43e8-89ec-7fc5c2d90226-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697521
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a9edc828-d2d0-442e-a9c8-7a5a0fdf1e4a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a9edc828-d2d0-442e-a9c8-7a5a0fdf1e4a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348760]
|
|
|
697522
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f99d5ad-c62b-438c-93e8-5cb4ff2abf13
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f99d5ad-c62b-438c-93e8-5cb4ff2abf13
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348761.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348761.0 (TID 348761) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-47fdffec-eff1-42ca-8538-fe02a7fd6782-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348761.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348761.0 (TID 348761) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-47fdffec-eff1-42ca-8538-fe02a7fd6782-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697523
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f99d5ad-c62b-438c-93e8-5cb4ff2abf13
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f99d5ad-c62b-438c-93e8-5cb4ff2abf13
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348761]
|
|
|
697524
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f113195-3f4a-4c02-8a66-8cacc8a96afb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f113195-3f4a-4c02-8a66-8cacc8a96afb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348762.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348762.0 (TID 348762) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ea53f557-6d3b-4fb7-8871-e0b285e6950c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348762.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348762.0 (TID 348762) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ea53f557-6d3b-4fb7-8871-e0b285e6950c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697525
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f113195-3f4a-4c02-8a66-8cacc8a96afb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f113195-3f4a-4c02-8a66-8cacc8a96afb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348762]
|
|
|
697526
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b93c91b0-7a7c-4643-94d2-256e217bba0e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b93c91b0-7a7c-4643-94d2-256e217bba0e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348763.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348763.0 (TID 348763) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ede89d8a-408f-4ce5-9a41-32c2d2fefe18-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348763.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348763.0 (TID 348763) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ede89d8a-408f-4ce5-9a41-32c2d2fefe18-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697527
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b93c91b0-7a7c-4643-94d2-256e217bba0e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b93c91b0-7a7c-4643-94d2-256e217bba0e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
11 ms
|
|
[348763]
|
|
|
697528
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b30dba6-b8f4-4b6f-93b3-accc0032d836
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b30dba6-b8f4-4b6f-93b3-accc0032d836
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348764.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348764.0 (TID 348764) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2a154e04-58e5-48ef-82f9-d8839fdcc496-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348764.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348764.0 (TID 348764) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2a154e04-58e5-48ef-82f9-d8839fdcc496-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697529
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b30dba6-b8f4-4b6f-93b3-accc0032d836
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b30dba6-b8f4-4b6f-93b3-accc0032d836
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
21 ms
|
|
[348764]
|
|
|
697530
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 09ff8740-0506-4485-b21a-583ccaf87b2d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 09ff8740-0506-4485-b21a-583ccaf87b2d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348765.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348765.0 (TID 348765) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-850e0a02-aeeb-45e7-9070-6e0663a8f8ba-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348765.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348765.0 (TID 348765) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-850e0a02-aeeb-45e7-9070-6e0663a8f8ba-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697531
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 09ff8740-0506-4485-b21a-583ccaf87b2d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 09ff8740-0506-4485-b21a-583ccaf87b2d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
17 ms
|
|
[348765]
|
|
|
697532
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 29cacbd3-e369-4c25-ac73-a4e3708c561f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 29cacbd3-e369-4c25-ac73-a4e3708c561f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
24 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348766.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348766.0 (TID 348766) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2f78c34b-183a-4ebe-9add-df2123b396c3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348766.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348766.0 (TID 348766) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2f78c34b-183a-4ebe-9add-df2123b396c3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697533
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 29cacbd3-e369-4c25-ac73-a4e3708c561f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 29cacbd3-e369-4c25-ac73-a4e3708c561f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:12
|
21 ms
|
|
[348766]
|
|
|
697534
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8a76a718-964e-43cf-8ac9-4c6ca5a310b2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8a76a718-964e-43cf-8ac9-4c6ca5a310b2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348767.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348767.0 (TID 348767) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fcd512ad-8974-4674-9512-6df1fc1f93f9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348767.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348767.0 (TID 348767) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fcd512ad-8974-4674-9512-6df1fc1f93f9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697535
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8a76a718-964e-43cf-8ac9-4c6ca5a310b2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8a76a718-964e-43cf-8ac9-4c6ca5a310b2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348767]
|
|
|
697536
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc53ef80-10da-4bdd-a556-2dfec9ad7f2d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc53ef80-10da-4bdd-a556-2dfec9ad7f2d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348768.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348768.0 (TID 348768) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-365212d0-9d20-4f56-9a77-093126697cb0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348768.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348768.0 (TID 348768) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-365212d0-9d20-4f56-9a77-093126697cb0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697537
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc53ef80-10da-4bdd-a556-2dfec9ad7f2d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc53ef80-10da-4bdd-a556-2dfec9ad7f2d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348768]
|
|
|
697538
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4ce35372-35b5-4923-9525-7228c6456085
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4ce35372-35b5-4923-9525-7228c6456085
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348769.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348769.0 (TID 348769) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1c0b3993-8371-4f4b-9fd2-5db29badfee6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348769.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348769.0 (TID 348769) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1c0b3993-8371-4f4b-9fd2-5db29badfee6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697539
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4ce35372-35b5-4923-9525-7228c6456085
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4ce35372-35b5-4923-9525-7228c6456085
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
14 ms
|
|
[348769]
|
|
|
697540
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 389672de-ffd1-4169-8f49-caf12709d838
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 389672de-ffd1-4169-8f49-caf12709d838
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348770.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348770.0 (TID 348770) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5c440d08-874f-47a8-855a-f6d003784661-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348770.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348770.0 (TID 348770) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5c440d08-874f-47a8-855a-f6d003784661-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697541
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 389672de-ffd1-4169-8f49-caf12709d838
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 389672de-ffd1-4169-8f49-caf12709d838
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
[348770]
|
|
|
697542
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 03882e09-0e17-4a51-a362-b67777f3fba3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 03882e09-0e17-4a51-a362-b67777f3fba3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348771.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348771.0 (TID 348771) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2bbc551d-6cd3-49e2-867f-cbc6d1360f1e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348771.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348771.0 (TID 348771) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2bbc551d-6cd3-49e2-867f-cbc6d1360f1e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697543
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 03882e09-0e17-4a51-a362-b67777f3fba3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 03882e09-0e17-4a51-a362-b67777f3fba3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
14 ms
|
|
[348771]
|
|
|
697544
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e037576-0b35-4ca4-9ac9-973e2bba79d7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e037576-0b35-4ca4-9ac9-973e2bba79d7
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348772.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348772.0 (TID 348772) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2439809b-ce62-4c3f-ad9d-619ea14eff36-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348772.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348772.0 (TID 348772) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2439809b-ce62-4c3f-ad9d-619ea14eff36-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697545
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e037576-0b35-4ca4-9ac9-973e2bba79d7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e037576-0b35-4ca4-9ac9-973e2bba79d7
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348772]
|
|
|
697546
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 44c19c72-1ba8-4b24-a20d-936d4764777d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 44c19c72-1ba8-4b24-a20d-936d4764777d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348773.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348773.0 (TID 348773) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5631231c-b53f-401f-b298-847ac43be863-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348773.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348773.0 (TID 348773) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5631231c-b53f-401f-b298-847ac43be863-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697547
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 44c19c72-1ba8-4b24-a20d-936d4764777d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 44c19c72-1ba8-4b24-a20d-936d4764777d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
14 ms
|
|
[348773]
|
|
|
697548
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 81c4e6b7-cd9c-4dcf-a8b6-fc5c855d34d9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 81c4e6b7-cd9c-4dcf-a8b6-fc5c855d34d9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
34 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348774.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348774.0 (TID 348774) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-447ec804-d92c-4b93-bd45-35c064bb9eb1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348774.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348774.0 (TID 348774) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-447ec804-d92c-4b93-bd45-35c064bb9eb1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697549
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 81c4e6b7-cd9c-4dcf-a8b6-fc5c855d34d9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 81c4e6b7-cd9c-4dcf-a8b6-fc5c855d34d9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
30 ms
|
|
[348774]
|
|
|
697550
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b7f3ff3b-7d7a-41b8-bb4c-3ae51b1cdd94
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b7f3ff3b-7d7a-41b8-bb4c-3ae51b1cdd94
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348775.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348775.0 (TID 348775) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-12ff9a71-1a93-47bf-bc74-ebc15ff344fb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348775.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348775.0 (TID 348775) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-12ff9a71-1a93-47bf-bc74-ebc15ff344fb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697551
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b7f3ff3b-7d7a-41b8-bb4c-3ae51b1cdd94
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b7f3ff3b-7d7a-41b8-bb4c-3ae51b1cdd94
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
12 ms
|
|
[348775]
|
|
|
697552
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3941ea8d-b978-4b86-95cc-c83f1948a5ba
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3941ea8d-b978-4b86-95cc-c83f1948a5ba
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348776.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348776.0 (TID 348776) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e2718b1-76ea-4552-bc74-cfffabef2415-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348776.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348776.0 (TID 348776) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e2718b1-76ea-4552-bc74-cfffabef2415-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697553
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3941ea8d-b978-4b86-95cc-c83f1948a5ba
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3941ea8d-b978-4b86-95cc-c83f1948a5ba
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348776]
|
|
|
697554
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a17c2f-0f20-424d-b0be-973b8056c11b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a17c2f-0f20-424d-b0be-973b8056c11b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348777.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348777.0 (TID 348777) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7899d85b-0c10-4b11-8301-873d5adc6b6e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348777.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348777.0 (TID 348777) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7899d85b-0c10-4b11-8301-873d5adc6b6e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697555
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a17c2f-0f20-424d-b0be-973b8056c11b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a17c2f-0f20-424d-b0be-973b8056c11b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
12 ms
|
|
[348777]
|
|
|
697556
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc63525b-cbba-474e-9775-3d2a40b60498
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc63525b-cbba-474e-9775-3d2a40b60498
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348778.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348778.0 (TID 348778) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-44a6ba6a-59c7-44b1-93cf-991173a08b39-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348778.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348778.0 (TID 348778) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-44a6ba6a-59c7-44b1-93cf-991173a08b39-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697557
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc63525b-cbba-474e-9775-3d2a40b60498
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc63525b-cbba-474e-9775-3d2a40b60498
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348778]
|
|
|
697558
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 95207162-3edf-44ba-9c8f-5dd7588645dd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 95207162-3edf-44ba-9c8f-5dd7588645dd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348779.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348779.0 (TID 348779) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ec02d18d-e701-4489-ae67-184e429d06be-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348779.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348779.0 (TID 348779) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ec02d18d-e701-4489-ae67-184e429d06be-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697559
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 95207162-3edf-44ba-9c8f-5dd7588645dd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 95207162-3edf-44ba-9c8f-5dd7588645dd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
12 ms
|
|
[348779]
|
|
|
697560
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6dea9408-f10d-43ce-bb65-98ac1791f86a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6dea9408-f10d-43ce-bb65-98ac1791f86a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348780.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348780.0 (TID 348780) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c15450da-41ed-4140-930e-b8e82976cd43-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348780.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348780.0 (TID 348780) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c15450da-41ed-4140-930e-b8e82976cd43-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697561
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6dea9408-f10d-43ce-bb65-98ac1791f86a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6dea9408-f10d-43ce-bb65-98ac1791f86a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
14 ms
|
|
[348780]
|
|
|
697562
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3ed66f6f-9347-4a25-a19d-3fa3267056dc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3ed66f6f-9347-4a25-a19d-3fa3267056dc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348781.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348781.0 (TID 348781) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-149f3762-30d3-4b60-8e56-5a053d7d60ff-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348781.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348781.0 (TID 348781) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-149f3762-30d3-4b60-8e56-5a053d7d60ff-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697563
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3ed66f6f-9347-4a25-a19d-3fa3267056dc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3ed66f6f-9347-4a25-a19d-3fa3267056dc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
14 ms
|
|
[348781]
|
|
|
697564
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eada2f49-185e-4db4-9ccc-91dc3638d8f1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eada2f49-185e-4db4-9ccc-91dc3638d8f1
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348782.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348782.0 (TID 348782) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5f834c1-f66a-415e-994a-6a3ccf203a85-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348782.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348782.0 (TID 348782) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5f834c1-f66a-415e-994a-6a3ccf203a85-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697565
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eada2f49-185e-4db4-9ccc-91dc3638d8f1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eada2f49-185e-4db4-9ccc-91dc3638d8f1
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
12 ms
|
|
[348782]
|
|
|
697566
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30b7b6d-8acb-4c0a-9d3f-3aad444fc68a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30b7b6d-8acb-4c0a-9d3f-3aad444fc68a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348783.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348783.0 (TID 348783) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac74970e-e8f0-4bfa-9895-23cf5ca82c40-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348783.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348783.0 (TID 348783) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac74970e-e8f0-4bfa-9895-23cf5ca82c40-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697567
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30b7b6d-8acb-4c0a-9d3f-3aad444fc68a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a30b7b6d-8acb-4c0a-9d3f-3aad444fc68a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348783]
|
|
|
697568
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 07089a3b-cf29-42d4-a3d4-9a745354bfec
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 07089a3b-cf29-42d4-a3d4-9a745354bfec
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
29 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348784.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348784.0 (TID 348784) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5b268425-3fd7-45c5-be13-64dcc15f2cbc-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348784.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348784.0 (TID 348784) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5b268425-3fd7-45c5-be13-64dcc15f2cbc-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697569
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 07089a3b-cf29-42d4-a3d4-9a745354bfec
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 07089a3b-cf29-42d4-a3d4-9a745354bfec
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
26 ms
|
|
[348784]
|
|
|
697570
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 458b782c-76d6-4503-a0ea-0b0ebf390b1a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 458b782c-76d6-4503-a0ea-0b0ebf390b1a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348785.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348785.0 (TID 348785) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4a7c0bb6-1c74-4e57-bb82-7d992e64ef90-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348785.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348785.0 (TID 348785) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4a7c0bb6-1c74-4e57-bb82-7d992e64ef90-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697571
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 458b782c-76d6-4503-a0ea-0b0ebf390b1a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 458b782c-76d6-4503-a0ea-0b0ebf390b1a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348785]
|
|
|
697572
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84cda1d1-180b-4912-bb3d-a2e4ace33936
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84cda1d1-180b-4912-bb3d-a2e4ace33936
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348786.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348786.0 (TID 348786) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-847e4b62-c6b0-4972-b7b8-8d3a55a711ab-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348786.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348786.0 (TID 348786) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-847e4b62-c6b0-4972-b7b8-8d3a55a711ab-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697573
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84cda1d1-180b-4912-bb3d-a2e4ace33936
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84cda1d1-180b-4912-bb3d-a2e4ace33936
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
14 ms
|
|
[348786]
|
|
|
697574
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078f9abd-ad41-4a51-9352-7fb261767483
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078f9abd-ad41-4a51-9352-7fb261767483
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348787.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348787.0 (TID 348787) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a0a3a509-77de-4976-a9a6-2530ce76501a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348787.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348787.0 (TID 348787) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a0a3a509-77de-4976-a9a6-2530ce76501a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697575
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078f9abd-ad41-4a51-9352-7fb261767483
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078f9abd-ad41-4a51-9352-7fb261767483
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
12 ms
|
|
[348787]
|
|
|
697576
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a3239cf1-1cda-48b0-bc42-dd402a8df2de
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a3239cf1-1cda-48b0-bc42-dd402a8df2de
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348788.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348788.0 (TID 348788) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f00d7d56-730f-49c7-9674-aa16997d6a53-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348788.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348788.0 (TID 348788) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f00d7d56-730f-49c7-9674-aa16997d6a53-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697577
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a3239cf1-1cda-48b0-bc42-dd402a8df2de
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a3239cf1-1cda-48b0-bc42-dd402a8df2de
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
13 ms
|
|
[348788]
|
|
|
697578
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26c0cf80-0449-4fb6-b3ee-f390831da63a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26c0cf80-0449-4fb6-b3ee-f390831da63a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
29 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348789.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348789.0 (TID 348789) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-148eaa9b-c92c-4dfd-8f42-b8ebcfbdcaeb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348789.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348789.0 (TID 348789) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-148eaa9b-c92c-4dfd-8f42-b8ebcfbdcaeb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697579
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26c0cf80-0449-4fb6-b3ee-f390831da63a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26c0cf80-0449-4fb6-b3ee-f390831da63a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:13
|
26 ms
|
|
[348789]
|
|
|
697580
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 521fce52-d50f-4d15-a25c-a626bb1a9660
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 521fce52-d50f-4d15-a25c-a626bb1a9660
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348790.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348790.0 (TID 348790) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b8649882-aea4-4060-bef9-d9110756a66d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348790.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348790.0 (TID 348790) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b8649882-aea4-4060-bef9-d9110756a66d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697581
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 521fce52-d50f-4d15-a25c-a626bb1a9660
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 521fce52-d50f-4d15-a25c-a626bb1a9660
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
12 ms
|
|
[348790]
|
|
|
697582
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6a2d6bbb-b7a4-4051-816c-59a1f2943aa5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6a2d6bbb-b7a4-4051-816c-59a1f2943aa5
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348791.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348791.0 (TID 348791) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a7184caa-61ce-4846-b261-9025296c68fb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348791.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348791.0 (TID 348791) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a7184caa-61ce-4846-b261-9025296c68fb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697583
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6a2d6bbb-b7a4-4051-816c-59a1f2943aa5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6a2d6bbb-b7a4-4051-816c-59a1f2943aa5
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
12 ms
|
|
[348791]
|
|
|
697584
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d473de28-c3e4-4960-bdce-dc95933c4669
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d473de28-c3e4-4960-bdce-dc95933c4669
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348792.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348792.0 (TID 348792) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2a2c5545-be35-4fdb-929e-bee52fe37744-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348792.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348792.0 (TID 348792) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2a2c5545-be35-4fdb-929e-bee52fe37744-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697585
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d473de28-c3e4-4960-bdce-dc95933c4669
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d473de28-c3e4-4960-bdce-dc95933c4669
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
13 ms
|
|
[348792]
|
|
|
697586
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 410d6aea-5005-42f7-bf79-aefd3188b583
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 410d6aea-5005-42f7-bf79-aefd3188b583
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348793.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348793.0 (TID 348793) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-79cfb85e-53b0-492d-a8cf-c9ae93f7c094-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348793.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348793.0 (TID 348793) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-79cfb85e-53b0-492d-a8cf-c9ae93f7c094-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697587
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 410d6aea-5005-42f7-bf79-aefd3188b583
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 410d6aea-5005-42f7-bf79-aefd3188b583
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
12 ms
|
|
[348793]
|
|
|
697588
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bd12e967-b332-467c-b280-effc3d8d7e93
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bd12e967-b332-467c-b280-effc3d8d7e93
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
33 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348794.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348794.0 (TID 348794) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-807772c0-d3ee-4424-b1b0-63c5c2c284f3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348794.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348794.0 (TID 348794) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-807772c0-d3ee-4424-b1b0-63c5c2c284f3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697589
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bd12e967-b332-467c-b280-effc3d8d7e93
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bd12e967-b332-467c-b280-effc3d8d7e93
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
30 ms
|
|
[348794]
|
|
|
697590
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 028f2d39-b23d-4831-88d8-0ef8dbb6bf81
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 028f2d39-b23d-4831-88d8-0ef8dbb6bf81
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348795.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348795.0 (TID 348795) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b936e6e1-a7f7-4538-91f4-b537c3b39668-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348795.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348795.0 (TID 348795) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b936e6e1-a7f7-4538-91f4-b537c3b39668-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697591
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 028f2d39-b23d-4831-88d8-0ef8dbb6bf81
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 028f2d39-b23d-4831-88d8-0ef8dbb6bf81
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
11 ms
|
|
[348795]
|
|
|
697592
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 93347b9d-3a5e-4119-997c-252db12e5bf6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 93347b9d-3a5e-4119-997c-252db12e5bf6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348796.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348796.0 (TID 348796) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d7022076-d4a9-44ec-a5df-7b2e499489c1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348796.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348796.0 (TID 348796) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d7022076-d4a9-44ec-a5df-7b2e499489c1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697593
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 93347b9d-3a5e-4119-997c-252db12e5bf6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 93347b9d-3a5e-4119-997c-252db12e5bf6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
12 ms
|
|
[348796]
|
|
|
697594
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2e9b2865-3a14-40ab-916b-85d874847838
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2e9b2865-3a14-40ab-916b-85d874847838
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348797.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348797.0 (TID 348797) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-154b0c46-7d45-41bd-b536-ef498922f7b0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348797.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348797.0 (TID 348797) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-154b0c46-7d45-41bd-b536-ef498922f7b0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697595
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2e9b2865-3a14-40ab-916b-85d874847838
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2e9b2865-3a14-40ab-916b-85d874847838
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
14 ms
|
|
[348797]
|
|
|
697596
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5092de86-b57d-4a6b-958c-128a255460c2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5092de86-b57d-4a6b-958c-128a255460c2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348798.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348798.0 (TID 348798) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aecd3973-484d-4c55-b814-1a8b140a90cf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348798.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348798.0 (TID 348798) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aecd3973-484d-4c55-b814-1a8b140a90cf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697597
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5092de86-b57d-4a6b-958c-128a255460c2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5092de86-b57d-4a6b-958c-128a255460c2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
12 ms
|
|
[348798]
|
|
|
697598
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3208f69a-c87b-47b8-a8d0-83817046c950
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3208f69a-c87b-47b8-a8d0-83817046c950
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348799.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348799.0 (TID 348799) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aab20a1c-a753-4a01-93c9-8041cff6a705-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348799.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348799.0 (TID 348799) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aab20a1c-a753-4a01-93c9-8041cff6a705-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697599
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3208f69a-c87b-47b8-a8d0-83817046c950
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3208f69a-c87b-47b8-a8d0-83817046c950
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
13 ms
|
|
[348799]
|
|
|
697600
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 209b4e7c-88db-48ce-90b6-7a9f1a110bac
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 209b4e7c-88db-48ce-90b6-7a9f1a110bac
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348800.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348800.0 (TID 348800) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cea3fc84-cdcb-4e10-8099-3bab349ccd39-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348800.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348800.0 (TID 348800) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cea3fc84-cdcb-4e10-8099-3bab349ccd39-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697601
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 209b4e7c-88db-48ce-90b6-7a9f1a110bac
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 209b4e7c-88db-48ce-90b6-7a9f1a110bac
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
11 ms
|
|
[348800]
|
|
|
697602
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cd06003e-19e4-407c-abe2-95b085faacdd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cd06003e-19e4-407c-abe2-95b085faacdd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348801.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348801.0 (TID 348801) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-614b27a1-ee50-4798-84de-a1aee372bda4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348801.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348801.0 (TID 348801) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-614b27a1-ee50-4798-84de-a1aee372bda4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697603
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cd06003e-19e4-407c-abe2-95b085faacdd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cd06003e-19e4-407c-abe2-95b085faacdd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
12 ms
|
|
[348801]
|
|
|
697604
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43687223-1631-43e9-a122-d7324e2afbab
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43687223-1631-43e9-a122-d7324e2afbab
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348802.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348802.0 (TID 348802) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-699ed537-ec7a-43f2-96cb-2429a1bf3a79-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348802.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348802.0 (TID 348802) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-699ed537-ec7a-43f2-96cb-2429a1bf3a79-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697605
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43687223-1631-43e9-a122-d7324e2afbab
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43687223-1631-43e9-a122-d7324e2afbab
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
10 ms
|
|
[348802]
|
|
|
697606
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31bb5797-dca9-4f5d-9677-47ec814e1d79
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31bb5797-dca9-4f5d-9677-47ec814e1d79
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
22 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348803.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348803.0 (TID 348803) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7bfc6f84-9b38-4568-abc3-ab450dab398c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348803.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348803.0 (TID 348803) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7bfc6f84-9b38-4568-abc3-ab450dab398c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697607
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31bb5797-dca9-4f5d-9677-47ec814e1d79
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31bb5797-dca9-4f5d-9677-47ec814e1d79
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
20 ms
|
|
[348803]
|
|
|
697608
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7a80ffd3-3c55-4f4f-b712-a2ac75b356fa
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7a80ffd3-3c55-4f4f-b712-a2ac75b356fa
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348804.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348804.0 (TID 348804) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac1bad98-2136-437b-bcf5-f808b52c6bb4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348804.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348804.0 (TID 348804) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac1bad98-2136-437b-bcf5-f808b52c6bb4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697609
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7a80ffd3-3c55-4f4f-b712-a2ac75b356fa
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7a80ffd3-3c55-4f4f-b712-a2ac75b356fa
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
20 ms
|
|
[348804]
|
|
|
697610
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab3a0b5d-c71a-41d3-bef3-3964f0356618
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab3a0b5d-c71a-41d3-bef3-3964f0356618
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348805.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348805.0 (TID 348805) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2f834d2-4cfb-4828-982a-30166316e2f1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348805.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348805.0 (TID 348805) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2f834d2-4cfb-4828-982a-30166316e2f1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697611
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab3a0b5d-c71a-41d3-bef3-3964f0356618
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab3a0b5d-c71a-41d3-bef3-3964f0356618
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
11 ms
|
|
[348805]
|
|
|
697612
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e31bc11c-cf09-4c2d-9fbe-296ab306c04f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e31bc11c-cf09-4c2d-9fbe-296ab306c04f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348806.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348806.0 (TID 348806) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d9a0e9dd-dbbb-4ae7-b04a-7417adbc50ad-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348806.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348806.0 (TID 348806) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d9a0e9dd-dbbb-4ae7-b04a-7417adbc50ad-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697613
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e31bc11c-cf09-4c2d-9fbe-296ab306c04f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e31bc11c-cf09-4c2d-9fbe-296ab306c04f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
11 ms
|
|
[348806]
|
|
|
697614
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e71ab3d6-016a-49a3-9a87-63c00e0ae3d0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e71ab3d6-016a-49a3-9a87-63c00e0ae3d0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348807.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348807.0 (TID 348807) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dcccde62-c31c-41b0-a6c2-5d8385e63395-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348807.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348807.0 (TID 348807) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dcccde62-c31c-41b0-a6c2-5d8385e63395-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697615
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e71ab3d6-016a-49a3-9a87-63c00e0ae3d0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e71ab3d6-016a-49a3-9a87-63c00e0ae3d0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
11 ms
|
|
[348807]
|
|
|
697616
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 11c9a03e-b591-4b9a-9d71-c17503d9cb95
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 11c9a03e-b591-4b9a-9d71-c17503d9cb95
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348808.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348808.0 (TID 348808) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8330b8de-8e18-4ccb-91ae-2090370889aa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348808.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348808.0 (TID 348808) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8330b8de-8e18-4ccb-91ae-2090370889aa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697617
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 11c9a03e-b591-4b9a-9d71-c17503d9cb95
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 11c9a03e-b591-4b9a-9d71-c17503d9cb95
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
13 ms
|
|
[348808]
|
|
|
697618
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d297b8a-5cc3-40df-a8ab-7b84c0b72c13
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d297b8a-5cc3-40df-a8ab-7b84c0b72c13
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348809.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348809.0 (TID 348809) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3fe745d5-6489-4ad7-9c14-a2a81a5a3a72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348809.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348809.0 (TID 348809) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3fe745d5-6489-4ad7-9c14-a2a81a5a3a72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697619
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d297b8a-5cc3-40df-a8ab-7b84c0b72c13
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d297b8a-5cc3-40df-a8ab-7b84c0b72c13
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
12 ms
|
|
[348809]
|
|
|
697620
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3485c00-dbf4-43cf-b0dc-2d71c3ca3cda
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3485c00-dbf4-43cf-b0dc-2d71c3ca3cda
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348810.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348810.0 (TID 348810) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-23a4558f-c065-4b2d-ae0b-13f5b7996881-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348810.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348810.0 (TID 348810) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-23a4558f-c065-4b2d-ae0b-13f5b7996881-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697621
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3485c00-dbf4-43cf-b0dc-2d71c3ca3cda
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3485c00-dbf4-43cf-b0dc-2d71c3ca3cda
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
17 ms
|
|
[348810]
|
|
|
697622
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ea9c335-16bb-4d82-b5ed-fa8d7790aadb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ea9c335-16bb-4d82-b5ed-fa8d7790aadb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348811.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348811.0 (TID 348811) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e5a30dc0-c65b-4efd-bdff-acfcaa3b5af7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348811.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348811.0 (TID 348811) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e5a30dc0-c65b-4efd-bdff-acfcaa3b5af7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697623
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ea9c335-16bb-4d82-b5ed-fa8d7790aadb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ea9c335-16bb-4d82-b5ed-fa8d7790aadb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
18 ms
|
|
[348811]
|
|
|
697624
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00310494-518e-45c9-8a89-9dcee6f6835f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00310494-518e-45c9-8a89-9dcee6f6835f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348812.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348812.0 (TID 348812) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1406a963-1121-46c9-bf0a-466e11523a7f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348812.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348812.0 (TID 348812) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1406a963-1121-46c9-bf0a-466e11523a7f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697625
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00310494-518e-45c9-8a89-9dcee6f6835f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00310494-518e-45c9-8a89-9dcee6f6835f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:14
|
15 ms
|
|
[348812]
|
|
|
697626
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c339ab21-7c1d-49ea-8843-4fada2088d6d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c339ab21-7c1d-49ea-8843-4fada2088d6d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348813.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348813.0 (TID 348813) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6054637c-dbd3-435b-84b1-5a7f9ec3fdfb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348813.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348813.0 (TID 348813) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6054637c-dbd3-435b-84b1-5a7f9ec3fdfb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697627
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c339ab21-7c1d-49ea-8843-4fada2088d6d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c339ab21-7c1d-49ea-8843-4fada2088d6d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348813]
|
|
|
697628
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3626b6f3-d752-4395-88ad-b2bcb0c83e73
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3626b6f3-d752-4395-88ad-b2bcb0c83e73
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
27 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348814.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348814.0 (TID 348814) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0046e058-e31f-4904-bbf0-29c02c89dd40-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348814.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348814.0 (TID 348814) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0046e058-e31f-4904-bbf0-29c02c89dd40-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697629
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3626b6f3-d752-4395-88ad-b2bcb0c83e73
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3626b6f3-d752-4395-88ad-b2bcb0c83e73
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
24 ms
|
|
[348814]
|
|
|
697630
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8eeaf024-cd06-4c61-af53-6dab863f6217
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8eeaf024-cd06-4c61-af53-6dab863f6217
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348815.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348815.0 (TID 348815) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-87cd3326-220c-4b06-9093-fb6b2057bdea-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348815.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348815.0 (TID 348815) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-87cd3326-220c-4b06-9093-fb6b2057bdea-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697631
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8eeaf024-cd06-4c61-af53-6dab863f6217
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8eeaf024-cd06-4c61-af53-6dab863f6217
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348815]
|
|
|
697632
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89f4c716-c057-4e4d-9466-31d6c1880fb0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89f4c716-c057-4e4d-9466-31d6c1880fb0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348816.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348816.0 (TID 348816) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5b341c91-6e13-4529-a9b3-79c82391a97c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348816.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348816.0 (TID 348816) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5b341c91-6e13-4529-a9b3-79c82391a97c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697633
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89f4c716-c057-4e4d-9466-31d6c1880fb0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89f4c716-c057-4e4d-9466-31d6c1880fb0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
12 ms
|
|
[348816]
|
|
|
697634
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d90ac1ad-2c68-4e17-9812-ec15cc364abb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d90ac1ad-2c68-4e17-9812-ec15cc364abb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348817.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348817.0 (TID 348817) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-de037436-978c-40e3-a26b-f34cf20e0ae0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348817.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348817.0 (TID 348817) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-de037436-978c-40e3-a26b-f34cf20e0ae0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697635
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d90ac1ad-2c68-4e17-9812-ec15cc364abb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d90ac1ad-2c68-4e17-9812-ec15cc364abb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
14 ms
|
|
[348817]
|
|
|
697636
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 32c67a00-27cd-434e-9037-4f0f45c0a8f4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 32c67a00-27cd-434e-9037-4f0f45c0a8f4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348818.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348818.0 (TID 348818) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dd56fd1d-5d9d-405d-994f-526807bd5750-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348818.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348818.0 (TID 348818) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dd56fd1d-5d9d-405d-994f-526807bd5750-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697637
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 32c67a00-27cd-434e-9037-4f0f45c0a8f4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 32c67a00-27cd-434e-9037-4f0f45c0a8f4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348818]
|
|
|
697638
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d18a6d81-346c-4ba2-90da-12174cae53ef
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d18a6d81-346c-4ba2-90da-12174cae53ef
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348819.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348819.0 (TID 348819) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-83d58aa0-eefd-4049-96e2-b98220eb6bec-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348819.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348819.0 (TID 348819) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-83d58aa0-eefd-4049-96e2-b98220eb6bec-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697639
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d18a6d81-346c-4ba2-90da-12174cae53ef
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d18a6d81-346c-4ba2-90da-12174cae53ef
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
14 ms
|
|
[348819]
|
|
|
697640
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e383b4a6-21a9-491c-a6ed-3fa4a7ec736d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e383b4a6-21a9-491c-a6ed-3fa4a7ec736d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348820.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348820.0 (TID 348820) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7bd0a224-2cf8-477b-8be2-99e6618b3993-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348820.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348820.0 (TID 348820) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7bd0a224-2cf8-477b-8be2-99e6618b3993-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697641
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e383b4a6-21a9-491c-a6ed-3fa4a7ec736d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e383b4a6-21a9-491c-a6ed-3fa4a7ec736d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348820]
|
|
|
697642
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3804a2ab-cfdd-4237-bee8-dc4074a01cc9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3804a2ab-cfdd-4237-bee8-dc4074a01cc9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
18 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348821.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348821.0 (TID 348821) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0686df66-271d-42c7-baf8-89bdfe7e5ad7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348821.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348821.0 (TID 348821) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0686df66-271d-42c7-baf8-89bdfe7e5ad7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697643
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3804a2ab-cfdd-4237-bee8-dc4074a01cc9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3804a2ab-cfdd-4237-bee8-dc4074a01cc9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
15 ms
|
|
[348821]
|
|
|
697644
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a2255a50-d493-4a42-a820-1b97795cc7c0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a2255a50-d493-4a42-a820-1b97795cc7c0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
18 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348822.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348822.0 (TID 348822) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-55d0a1c6-bf97-4a38-894c-df0c2e82524c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348822.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348822.0 (TID 348822) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-55d0a1c6-bf97-4a38-894c-df0c2e82524c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697645
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a2255a50-d493-4a42-a820-1b97795cc7c0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a2255a50-d493-4a42-a820-1b97795cc7c0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
14 ms
|
|
[348822]
|
|
|
697646
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3075048d-e69d-4842-840f-c206e23bfb5f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3075048d-e69d-4842-840f-c206e23bfb5f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348823.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348823.0 (TID 348823) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6e727177-443a-47ca-ab6e-4542898479d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348823.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348823.0 (TID 348823) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6e727177-443a-47ca-ab6e-4542898479d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697647
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3075048d-e69d-4842-840f-c206e23bfb5f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3075048d-e69d-4842-840f-c206e23bfb5f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348823]
|
|
|
697648
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc775baf-b6ea-4738-b643-0de835f15cf9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc775baf-b6ea-4738-b643-0de835f15cf9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
34 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348824.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348824.0 (TID 348824) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6d3f3de9-23ca-48cf-8b29-bef209ab21b8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348824.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348824.0 (TID 348824) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6d3f3de9-23ca-48cf-8b29-bef209ab21b8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697649
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc775baf-b6ea-4738-b643-0de835f15cf9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cc775baf-b6ea-4738-b643-0de835f15cf9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
31 ms
|
|
[348824]
|
|
|
697650
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 553e6b80-d06c-49ab-b92a-24707a966304
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 553e6b80-d06c-49ab-b92a-24707a966304
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348825.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348825.0 (TID 348825) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4b40eae0-e658-4692-96fd-1e2954e2fb0f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348825.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348825.0 (TID 348825) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4b40eae0-e658-4692-96fd-1e2954e2fb0f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697651
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 553e6b80-d06c-49ab-b92a-24707a966304
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 553e6b80-d06c-49ab-b92a-24707a966304
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
12 ms
|
|
[348825]
|
|
|
697652
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ed411509-c649-487a-90fb-2c3d50a95165
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ed411509-c649-487a-90fb-2c3d50a95165
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348826.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348826.0 (TID 348826) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5ea368fc-d5e8-4896-a067-3131afc5c109-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348826.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348826.0 (TID 348826) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5ea368fc-d5e8-4896-a067-3131afc5c109-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697653
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ed411509-c649-487a-90fb-2c3d50a95165
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ed411509-c649-487a-90fb-2c3d50a95165
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348826]
|
|
|
697654
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 636ac0a7-5b20-407c-9870-26ba6999c71b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 636ac0a7-5b20-407c-9870-26ba6999c71b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348827.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348827.0 (TID 348827) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f4a341f0-4d8f-4aff-afa0-d36ac1f446a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348827.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348827.0 (TID 348827) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f4a341f0-4d8f-4aff-afa0-d36ac1f446a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697655
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 636ac0a7-5b20-407c-9870-26ba6999c71b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 636ac0a7-5b20-407c-9870-26ba6999c71b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
12 ms
|
|
[348827]
|
|
|
697656
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c95a5d13-0ffc-416c-9b50-4a056d9fb774
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c95a5d13-0ffc-416c-9b50-4a056d9fb774
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348828.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348828.0 (TID 348828) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-41c1e25f-9130-4b06-9ab6-4a31a4d181f2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348828.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348828.0 (TID 348828) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-41c1e25f-9130-4b06-9ab6-4a31a4d181f2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697657
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c95a5d13-0ffc-416c-9b50-4a056d9fb774
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c95a5d13-0ffc-416c-9b50-4a056d9fb774
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348828]
|
|
|
697658
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5178991c-3fe0-467f-a4d3-d4082c16ef04
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5178991c-3fe0-467f-a4d3-d4082c16ef04
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348829.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348829.0 (TID 348829) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e6ca37dd-dba2-42eb-b90d-7896509b2578-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348829.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348829.0 (TID 348829) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e6ca37dd-dba2-42eb-b90d-7896509b2578-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697659
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5178991c-3fe0-467f-a4d3-d4082c16ef04
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5178991c-3fe0-467f-a4d3-d4082c16ef04
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
13 ms
|
|
[348829]
|
|
|
697660
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9dbec940-c72e-48d3-88cc-ccd989c3b244
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9dbec940-c72e-48d3-88cc-ccd989c3b244
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348830.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348830.0 (TID 348830) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c340655-2587-417a-9383-bb479f71c94d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348830.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348830.0 (TID 348830) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c340655-2587-417a-9383-bb479f71c94d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697661
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9dbec940-c72e-48d3-88cc-ccd989c3b244
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9dbec940-c72e-48d3-88cc-ccd989c3b244
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
14 ms
|
|
[348830]
|
|
|
697662
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ca279e38-17c5-47a9-bb81-1e8715f54bda
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ca279e38-17c5-47a9-bb81-1e8715f54bda
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348831.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348831.0 (TID 348831) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-85c6a210-b0e9-40fe-b635-0b0d7dd1077a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348831.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348831.0 (TID 348831) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-85c6a210-b0e9-40fe-b635-0b0d7dd1077a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697663
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ca279e38-17c5-47a9-bb81-1e8715f54bda
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ca279e38-17c5-47a9-bb81-1e8715f54bda
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
19 ms
|
|
[348831]
|
|
|
697664
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 995464bf-6e86-46d7-89c8-0f9d4a3e1e32
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 995464bf-6e86-46d7-89c8-0f9d4a3e1e32
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348832.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348832.0 (TID 348832) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c1492f07-1290-4c9e-a98e-d6604ee87103-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348832.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348832.0 (TID 348832) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c1492f07-1290-4c9e-a98e-d6604ee87103-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697665
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 995464bf-6e86-46d7-89c8-0f9d4a3e1e32
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 995464bf-6e86-46d7-89c8-0f9d4a3e1e32
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
11 ms
|
|
[348832]
|
|
|
697666
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9a682599-c2b6-412c-9795-0493491aa29a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9a682599-c2b6-412c-9795-0493491aa29a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348833.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348833.0 (TID 348833) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d9ce6409-296a-4ec5-bf3d-1439fa0d52f8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348833.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348833.0 (TID 348833) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d9ce6409-296a-4ec5-bf3d-1439fa0d52f8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697667
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9a682599-c2b6-412c-9795-0493491aa29a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9a682599-c2b6-412c-9795-0493491aa29a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
14 ms
|
|
[348833]
|
|
|
697668
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 73f74117-b6ad-40b7-a667-6ff18fcc7df9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 73f74117-b6ad-40b7-a667-6ff18fcc7df9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
27 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348834.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348834.0 (TID 348834) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ed335bcf-6ab5-4925-a519-f38f448d30e1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348834.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348834.0 (TID 348834) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ed335bcf-6ab5-4925-a519-f38f448d30e1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697669
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 73f74117-b6ad-40b7-a667-6ff18fcc7df9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 73f74117-b6ad-40b7-a667-6ff18fcc7df9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:15
|
24 ms
|
|
[348834]
|
|
|
697670
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 097686fb-cead-435a-adc3-f04439654022
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 097686fb-cead-435a-adc3-f04439654022
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348835.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348835.0 (TID 348835) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9cd1d7f8-fcbc-4017-92e7-133fcd112742-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348835.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348835.0 (TID 348835) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9cd1d7f8-fcbc-4017-92e7-133fcd112742-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697671
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 097686fb-cead-435a-adc3-f04439654022
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 097686fb-cead-435a-adc3-f04439654022
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
[348835]
|
|
|
697672
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00dd1a4e-5fd1-4fb6-a0c8-a393f09d1c09
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00dd1a4e-5fd1-4fb6-a0c8-a393f09d1c09
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348836.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348836.0 (TID 348836) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d1b158bd-c016-42f4-ab5d-51e93842739d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348836.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348836.0 (TID 348836) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d1b158bd-c016-42f4-ab5d-51e93842739d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697673
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00dd1a4e-5fd1-4fb6-a0c8-a393f09d1c09
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 00dd1a4e-5fd1-4fb6-a0c8-a393f09d1c09
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
[348836]
|
|
|
697674
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = af139896-ace6-4695-a568-3263b57ad567
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = af139896-ace6-4695-a568-3263b57ad567
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348837.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348837.0 (TID 348837) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a1f026b5-a67e-4cf0-a2c8-82fd3212744e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348837.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348837.0 (TID 348837) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a1f026b5-a67e-4cf0-a2c8-82fd3212744e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697675
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = af139896-ace6-4695-a568-3263b57ad567
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = af139896-ace6-4695-a568-3263b57ad567
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
[348837]
|
|
|
697676
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb773585-d444-48c0-b566-edd1ed278cd5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb773585-d444-48c0-b566-edd1ed278cd5
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348838.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348838.0 (TID 348838) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6026bf73-0a6a-45ff-ad79-bf181cc0b01b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348838.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348838.0 (TID 348838) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6026bf73-0a6a-45ff-ad79-bf181cc0b01b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697677
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb773585-d444-48c0-b566-edd1ed278cd5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb773585-d444-48c0-b566-edd1ed278cd5
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
[348838]
|
|
|
697678
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3d9f995d-5466-4f75-a211-904d23bc6d27
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3d9f995d-5466-4f75-a211-904d23bc6d27
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348839.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348839.0 (TID 348839) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e34ef24-fff5-4b95-86cf-d56bb207cddf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348839.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348839.0 (TID 348839) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e34ef24-fff5-4b95-86cf-d56bb207cddf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697679
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3d9f995d-5466-4f75-a211-904d23bc6d27
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3d9f995d-5466-4f75-a211-904d23bc6d27
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
12 ms
|
|
[348839]
|
|
|
697680
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ed39dc-5bdc-4371-9cac-1128df3e700c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ed39dc-5bdc-4371-9cac-1128df3e700c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348840.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348840.0 (TID 348840) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-56f49ac9-5587-4906-a1ff-836d1235c063-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348840.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348840.0 (TID 348840) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-56f49ac9-5587-4906-a1ff-836d1235c063-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697681
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ed39dc-5bdc-4371-9cac-1128df3e700c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ed39dc-5bdc-4371-9cac-1128df3e700c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
[348840]
|
|
|
697682
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5fdfc6f1-98bb-4cf1-9024-3b4e955db130
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5fdfc6f1-98bb-4cf1-9024-3b4e955db130
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348841.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348841.0 (TID 348841) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5d3b4ae-b878-4da8-a9e3-e9c2bd5e1433-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348841.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348841.0 (TID 348841) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5d3b4ae-b878-4da8-a9e3-e9c2bd5e1433-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697683
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5fdfc6f1-98bb-4cf1-9024-3b4e955db130
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5fdfc6f1-98bb-4cf1-9024-3b4e955db130
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348841]
|
|
|
697684
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb3e8e69-193f-4535-8815-7c92bfab2f6a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb3e8e69-193f-4535-8815-7c92bfab2f6a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348842.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348842.0 (TID 348842) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-27f401bc-a9c9-467c-9a8e-cc4082200b98-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348842.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348842.0 (TID 348842) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-27f401bc-a9c9-467c-9a8e-cc4082200b98-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697685
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb3e8e69-193f-4535-8815-7c92bfab2f6a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb3e8e69-193f-4535-8815-7c92bfab2f6a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348842]
|
|
|
697686
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 639a0464-5b65-4bf9-97e4-da1957b548be
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 639a0464-5b65-4bf9-97e4-da1957b548be
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348843.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348843.0 (TID 348843) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e4846962-dd2e-4db8-8d64-5afa515ec0db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348843.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348843.0 (TID 348843) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e4846962-dd2e-4db8-8d64-5afa515ec0db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697687
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 639a0464-5b65-4bf9-97e4-da1957b548be
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 639a0464-5b65-4bf9-97e4-da1957b548be
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
10 ms
|
|
[348843]
|
|
|
697688
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d19379e-5d11-4917-826e-d70d6fcf6c1c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d19379e-5d11-4917-826e-d70d6fcf6c1c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
38 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348844.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348844.0 (TID 348844) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4ff2f810-e22f-4c73-99b0-3df4afb71473-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348844.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348844.0 (TID 348844) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4ff2f810-e22f-4c73-99b0-3df4afb71473-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697689
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d19379e-5d11-4917-826e-d70d6fcf6c1c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d19379e-5d11-4917-826e-d70d6fcf6c1c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
36 ms
|
|
[348844]
|
|
|
697690
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37fe2871-36eb-40bb-9f74-662766e43d5e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37fe2871-36eb-40bb-9f74-662766e43d5e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348845.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348845.0 (TID 348845) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b04acab6-9aae-461c-8fa2-eacddf891f94-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348845.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348845.0 (TID 348845) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b04acab6-9aae-461c-8fa2-eacddf891f94-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697691
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37fe2871-36eb-40bb-9f74-662766e43d5e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37fe2871-36eb-40bb-9f74-662766e43d5e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348845]
|
|
|
697692
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f234665-5d1b-4e55-8a13-763dd83fce99
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f234665-5d1b-4e55-8a13-763dd83fce99
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348846.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348846.0 (TID 348846) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-90db9dd3-3648-43a6-a50f-98f0e03fd975-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348846.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348846.0 (TID 348846) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-90db9dd3-3648-43a6-a50f-98f0e03fd975-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697693
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f234665-5d1b-4e55-8a13-763dd83fce99
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3f234665-5d1b-4e55-8a13-763dd83fce99
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
20 ms
|
|
[348846]
|
|
|
697694
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d345229d-9cdb-492b-aad3-d5665a903be8
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d345229d-9cdb-492b-aad3-d5665a903be8
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348847.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348847.0 (TID 348847) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-251eaa53-caed-4f1f-9caf-0bc4027a87dd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348847.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348847.0 (TID 348847) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-251eaa53-caed-4f1f-9caf-0bc4027a87dd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697695
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d345229d-9cdb-492b-aad3-d5665a903be8
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d345229d-9cdb-492b-aad3-d5665a903be8
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348847]
|
|
|
697696
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1aad6a10-163b-45c8-86aa-27e43c287f91
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1aad6a10-163b-45c8-86aa-27e43c287f91
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348848.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348848.0 (TID 348848) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8ec96738-e386-417a-85f8-f8b8278529bc-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348848.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348848.0 (TID 348848) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8ec96738-e386-417a-85f8-f8b8278529bc-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697697
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1aad6a10-163b-45c8-86aa-27e43c287f91
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1aad6a10-163b-45c8-86aa-27e43c287f91
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348848]
|
|
|
697698
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 53c99595-4005-4ec0-a310-2eb09b885919
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 53c99595-4005-4ec0-a310-2eb09b885919
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348849.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348849.0 (TID 348849) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d4e93d94-3640-448d-8b06-180590b49b61-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348849.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348849.0 (TID 348849) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d4e93d94-3640-448d-8b06-180590b49b61-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697699
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 53c99595-4005-4ec0-a310-2eb09b885919
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 53c99595-4005-4ec0-a310-2eb09b885919
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348849]
|
|
|
697700
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89116096-8ea5-407c-bee0-7ef18274c19a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89116096-8ea5-407c-bee0-7ef18274c19a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348850.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348850.0 (TID 348850) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4d62a9ca-d0d9-448b-b8ad-a8d58ae61c83-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348850.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348850.0 (TID 348850) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4d62a9ca-d0d9-448b-b8ad-a8d58ae61c83-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697701
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89116096-8ea5-407c-bee0-7ef18274c19a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89116096-8ea5-407c-bee0-7ef18274c19a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348850]
|
|
|
697702
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9d61466-be7c-44bf-aa9b-31dc70b710fa
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9d61466-be7c-44bf-aa9b-31dc70b710fa
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348851.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348851.0 (TID 348851) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0f861c1f-b0e3-47ac-8c00-ed207369e839-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348851.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348851.0 (TID 348851) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0f861c1f-b0e3-47ac-8c00-ed207369e839-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697703
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9d61466-be7c-44bf-aa9b-31dc70b710fa
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9d61466-be7c-44bf-aa9b-31dc70b710fa
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348851]
|
|
|
697704
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 321335ba-8bcd-4d5a-aedf-07289a29c5ca
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 321335ba-8bcd-4d5a-aedf-07289a29c5ca
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348852.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348852.0 (TID 348852) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5994acf1-9df6-4858-86fc-d1fdac922035-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348852.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348852.0 (TID 348852) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5994acf1-9df6-4858-86fc-d1fdac922035-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697705
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 321335ba-8bcd-4d5a-aedf-07289a29c5ca
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 321335ba-8bcd-4d5a-aedf-07289a29c5ca
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348852]
|
|
|
697706
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9f652a55-cbfe-4ca1-bb2a-e190819abd4f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9f652a55-cbfe-4ca1-bb2a-e190819abd4f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348853.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348853.0 (TID 348853) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5a87f620-2bc2-4183-9623-3918528ae814-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348853.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348853.0 (TID 348853) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5a87f620-2bc2-4183-9623-3918528ae814-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697707
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9f652a55-cbfe-4ca1-bb2a-e190819abd4f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9f652a55-cbfe-4ca1-bb2a-e190819abd4f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
11 ms
|
|
[348853]
|
|
|
697708
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 998f5383-35cf-4bc1-8fa8-5d7b09d0e498
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 998f5383-35cf-4bc1-8fa8-5d7b09d0e498
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
31 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 348854.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348854.0 (TID 348854) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-235bfb19-e225-442d-8b36-433d31625ec2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 348854.0 failed 1 times, most recent failure: Lost task 0.0 in stage 348854.0 (TID 348854) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-235bfb19-e225-442d-8b36-433d31625ec2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
697709
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 998f5383-35cf-4bc1-8fa8-5d7b09d0e498
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 998f5383-35cf-4bc1-8fa8-5d7b09d0e498
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 13:43:16
|
29 ms
|
|
[348854]
|
|